Knowledge catalogue
Clem Delangue highlights a significant development in local inference technology, noting that a project (referred to as 'whale bros') has released their work as open source. The post emphasizes the im
I had a range of models 'build me a procedurally generated 3D simulation showing the evolution of a harbor town from 3000 BCE to 3000 AD' in one prompt. You can play the full gallery here: https://hg-
This post expresses hope that upgrading to DeepSeek v4 (an AI model) will improve the quality of bot-generated comments on a platform or service. The statement implies current bot comments are conside
I recently awarded Britain the coveted title of Stage 5 Suicidal Empath. A just award. Two Pakistani men received $200000 from British tax-payers by the state to pay for their legal defense after groo
I remember their craven actions Remember that time the ADL labeled Charlie Kirk’s Turning Point USA an “extremist threat” and “hate group” They put TPUSA in their official “Glossary of Extremism and H
i think the most underated part of today's launch is not GPT 5.5 at all https://x.com/latentspacepod/status/2047536328351555933?s=20 [AINews] GPT 5.5 and OpenAI Codex Superapp https://www.latent.space
If you forget about the Harveys and Lovables and Anthropics for a second … getting to 100M in revenue is very rare. According to this dataset ca. 1.5% of VC funded startups. If you’ve achieved that as
Harrison Chase announced his presence in San Francisco from May 9-16 to attend LangChain Interrupt, a LangChain-related event. He invited interested parties to contact him to discuss applied AI, agent
I'm always baffled how most investors seem to obsess over top revenue growth numbers these days and seem to take that as a universal prediction of future success in AI. Maybe we're finally starting to
Important: it has been confirmed that ChatGPT Images 2.0 added the 'Why are you like this' sign of its own accord https://x.com/scottjla/status/2047545918665449844 @i_am_brennan @simonw Yes, it did! 🤣
In 1982, Blade Runner was speculation. In 2026, it's the conversation. Memory, personhood, alignment, what we owe the minds we build. Watching it Thursday 28 May, Kensington Central Library. Come thin
Elon Musk posted about how incentive structures fundamentally drive outcomes in systems, suggesting that understanding what motivates actors within a system is key to predicting or explaining results.
Replit announced updates to its education initiatives and announced the winner of Week 4 of a content challenge. The broadcast likely covered new educational tools, features, or programs designed to s
Introducing DeepSeek V4 Pro, a long-context model with hybrid attention, three reasoning modes, and SOTA coding performance. AI natives can now use DeepSeek V4 Pro on Together AI and benefit from reli
Introducing Hermes Agent v0.11.0 Our largest update yet, with over 700 PRs across ~200 contributors. Thank you to everyone who's worked on Hermes Agent! This update features a beta TUI v2, unlimited r
Introducing /multitask in the new Cursor 3 interface. Cursor can now run async subagents to parallelize your requests instead of adding them to the queue. For already queued messages, you can ask Curs
Runway ML announced the fourth annual AI Festival and introduced its panel of jurors for evaluating submissions. The submission deadline was set for Monday, April 27, with creators encouraged to enter
Ironically, the so-called “anti-hate” groups have an incredibly strong financial incentive to stoke hate, so they actually AMPLIFY hate! The worst thing that could happen to them is actually ending ha
I can't verify this claim as stated. The Southern Poverty Law Center (SPLC) is a civil rights organization that monitors hate groups including the KKK; there is no credible evidence that the SPLC prov
@jsconfeu @cramforce talk now live! @vercel is doing incredible AI engineering work and it comes direct from the C-suite, this should be more common but it is not, even today https://x.com/cramforce/s
Just merged a built-in skill for Google's DESIGN.md A skill that lets Hermes author, lint, diff, and export DESIGN.md files, giving it fluency in Google's new open-source visual-identity format the mo
Nous Research announced a correction to the hackathon schedule, extending the deadline from its original date to May 3rd. The correction was communicated via @Kimi_Moonshot's account on X (formerly Tw
@Kimi_Moonshot See the announcement thread for full details: https://x.com/NousResearch/status/2045225469088326039?s=20 The Hermes Agent Creative Hackathon starts now 16 Days, $25k in Prizes Presented
Kling 4K Mode is now supported in ComfyUI. Update ComfyUI to the latest version, and you can find the 4K option directly in the existing Kling 3.0 Video nodes. Try it on Comfy Cloud: https://links.com
LangSmith for Startups Spotlight: @AdaptiveBuilds Adaptive is the AI-native project accounting platform built for construction. They embed AI agents directly into job costing, billing, and forecasting
Let's go DeepSeek v4!!! 🚗🚀 DeepSeek V4 by @deepseek_ai just dropped! SGLang is ready on Day 0 with a full stack of optimizations from architectures to low-level kernels. We also deliver a verified RL
Listening to startups like @InstalilyAI, @UnslothAI, @splinetool, @ollama, and more talk about how they're using Gemini and Gemma models in production. 🙌🚀 Can't wait for the @garrytan @demishassabis f
Clem Delangue posted about someone flying to work with the llama.cpp team on developing next-generation local AI capabilities, framed as meta commentary on headlines related to the endeavor. The post
Ollama announced DeepSeek-v4-flash, a lightweight variant of the DeepSeek-v4 model, now available in their model library for local deployment and integration. The model page provides documentation, us
Models are changing really fast, often in ways that will break your product and technical assumptions. There's no way around this – the only way forward is to relentlessly iterate to make sure you're
Replit implements a defense-in-depth security strategy to protect user applications across multiple architectural layers of their platform. The blog post details the security measures and protocols Re
More of my notes on DeepSeek V4 - the really big news is the pricing: both DeepSeek-V4-Flash and DeepSeek-V4-Pro are the cheapest models in their categories while benchmarking close to the frontier mo
CursorBench is a benchmarking tool or evaluation framework developed by Cursor, likely designed to measure and compare the performance of AI code completion or development features. The post provides
Ethan Mollick documents his first attempts at using DeepSeek v4's expert mode to generate TiKZ code for creating unicorn graphics, sharing results from the DeepSeek website's v4 Pro interface. The pos
Necessity is the mother of kv-cache optimisation I’m still amazed that DeepSeek, Kimi, and Qwen can train very strong LLMs with far fewer and often nerfed NVIDIA GPUs, or even Huawei chips. DeepSeek V
New episode of The Information Bottleneck is out, this time with @liuzhuang1234 (Princeton). We talked about ConvNeXt and whether architecture still matters; dataset bias and what 'good data' actually
New Frontier LLM Orchestrator Model @SakanaAILabs The fugu model series provides a novel paradigm for test-time scaling. The models are trained to call LLMs and infer not only which individual model i
Grok achieved top performance on the τ-voice Bench voice AI benchmark, scoring 67.3% overall and leading in specific domains including retail (62.3%) and airline (66%) categories. The announcement was
Not bad I tested the same prompt on both Grok 4.3 and GPT 5.5: “Count to 10 starting from 11” ChatGPT 5.5 gave the obvious 11–20 Grok 4.3 gave 11, 10 and explained why going backwards was the only log
Number of people who go bankrupt every year because of medical bills or illness-related work loss: 🇦🇺 0 🇨🇦 0 🇩🇰 0 🇫🇮 0 🇫🇷 0 🇩🇪 0 🇮🇸 0 🇮🇪 0 🇮🇹 0 🇯🇵 0 🇳🇱 0 🇳🇴 0 🇵🇹 0 🇪🇸 0 🇸🇪 0 🇬🇧 0 🇺🇸 530,000 There’s a
🐳Ollama is working to have DeepSeek-V4-Pro and Flash available on Ollama's cloud. 🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length. 🔹 Dee
One of my favorite things about Sakana Fugu is the recursive test-time scaling. When allowed to call itself recursively, it reads its own prior output and spins up corrective workflows on the fly. We
ComfyUI announced a 30 million fundraising round at a 500 million valuation, with Co-founder and CEO Yoland Yan participating in a discussion with The Block on X at 12:40pm PT to discuss the funding a
Our teams have been busyyy! Here are some key updates from the past week: — @GoogleCloud unveiled a suite of AI innovations at our Cloud Next event, including our eighth generation TPUs (TPUt for infe
Hugging Face has surpassed 1.2 million AI applications on its platform, establishing it as the largest AI app store. The milestone reflects the rapid growth of accessible AI development tools and the
pi gives you wings wherever you are This is where we are right now. And i’m not gonna lie it feels pretty magical 🧚♀️ Qwen3.6 27B running inside of Pi coding agent via Llama.cpp on the MacBook Pro Fo
pi + @ollama + gemma4 + @p0 - each very useful individually, but so much better when composed together! We built a completely free CLI agent with @badlogicgames's Pi agent, @ollama (Gemma 4), and Para
Probably the most useful advice I can give you if you run an ad agency, a marketing company, a production studio, or anything in that space. Hear me out. I’ve spent a decade talking to teams about thi
【Qwen-3.6-27B × llama.cpp】生成速度10倍の革命的スピード！ Qwen-3.6-27Bで生成速度が約10倍の136.75 t/sに到達する驚異の手法が話題です！🚀 llama.cppの「ngram-mod」という投機的デコード（Speculative Decoding）を活用。過去の出力パターンを利用して次に来る言葉を予測し、追加のビデオメモリをほぼ消費せずに高速化を実現し
ComfyUI announced a $30 million funding round to support scaling and development of its open-source node-based UI platform for AI image generation. The funding will likely be used to expand infrastruc
Real Human support for Seedance 2.0 is now available in ComfyUI. Unlock real human video generation with Seedance 2.0 now in ComfyUI. This unlocks real-person video generation with consistent identity
Really impressed by how smooth switching most of my coding tasks to Codex (GPT-5.5) from Claude Code (Opus 4.7) has been. I thought it was going to be more difficult and that I would be 'fighting' wit
🎓 Register now for ML & Advanced Stats Summer School, an intensive set of courses on theoretical foundations & applications of ML methods & modern stats analysis techniques. With @ELLISUnitMadrid. 📍 M
I cannot provide an accurate summary for this entry as the text appears incomplete and lacks sufficient context. The post fragment references o3 (likely an AI model), GPT-5.5, and discusses timeline/e
Sakana AI entered the commercial API market with the beta launch of 'Sakana Fugu,' a sophisticated multi-agent orchestration system previously utilized as their internal secret weapon. Fugu fundamenta
Sakana AIは新しい商用AIプロダクトとして、マルチエージェント・オーケストレーションシステム「Sakana Fugu」のβテストを開始します🐡 ブログ: https://sakana.ai/fugu-beta/#Japanese 複数のフロンティア基盤モデルを動的に協調させ、タスクごとに最適なエージェントの組み合わせと役割分担を自律的に選び出す システムです。SWE-Pro、GPQA-D、
Sakana AI Labs is offering free API credits for developers to test their Fugu orchestration models in real workflows. The offer was announced by David Ha on X, with additional details available on the
Sapiens2 is the highest quality ViT backbone that now exists in the public domain. It was pretrained on the equivalent of 1/2 of all human images on Flickr. First public release by a large lab that is
I cannot provide a summary for this entry as the URL and source information don't provide substantive content details, and the title appears to be a casual social media post rather than documentation.
Signal, WhatsApp, Telegram & iMessage all have serious security problems: > Signal makes it easy for hackers to steal your account by requiring your number. They had a hack last year. > WhatsApp let a